{"id":"https://openalex.org/W2090584832","doi":"https://doi.org/10.1145/2155620.2155656","title":"Improving GPU performance via large warps and two-level warp scheduling","display_name":"Improving GPU performance via large warps and two-level warp scheduling","publication_year":2011,"publication_date":"2011-12-03","ids":{"openalex":"https://openalex.org/W2090584832","doi":"https://doi.org/10.1145/2155620.2155656","mag":"2090584832"},"language":"en","primary_location":{"id":"doi:10.1145/2155620.2155656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2155620.2155656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033116431","display_name":"Veynu Narasiman","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Veynu Narasiman","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas at Austin,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061066447","display_name":"Michael Shebanow","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Michael Shebanow","raw_affiliation_strings":["Nvidia Corporation","[NVIDIA Corporation, USA]"],"affiliations":[{"raw_affiliation_string":"Nvidia Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA Corporation, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052796636","display_name":"Chang Joo Lee","orcid":"https://orcid.org/0000-0003-2212-252X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chang Joo Lee","raw_affiliation_strings":["Intel Corporation","Intel Corp., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]},{"raw_affiliation_string":"Intel Corp., USA#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037488155","display_name":"Rustam Miftakhutdinov","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rustam Miftakhutdinov","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas at Austin,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon Univ (USA)"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon Univ (USA)","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070360563","display_name":"Yale N. Patt","orcid":"https://orcid.org/0009-0004-8704-8249"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yale N. Patt","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas at Austin,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033116431"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":24.65131524,"has_fulltext":false,"cited_by_count":414,"citation_normalized_percentile":{"value":0.9981125,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"308","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8851691484451294},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7767732739448547},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7306103706359863},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5831307768821716},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.537990391254425},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5306270122528076},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5246788859367371},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4514372646808624},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44084230065345764},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4122306704521179},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4101915955543518},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2853565812110901},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13128823041915894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851691484451294},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7767732739448547},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7306103706359863},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5831307768821716},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.537990391254425},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5306270122528076},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5246788859367371},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4514372646808624},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44084230065345764},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4122306704521179},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4101915955543518},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2853565812110901},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13128823041915894},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2155620.2155656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2155620.2155656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1601753226","https://openalex.org/W1762731526","https://openalex.org/W1990800384","https://openalex.org/W1992851788","https://openalex.org/W2000335122","https://openalex.org/W2012252449","https://openalex.org/W2048583641","https://openalex.org/W2069976976","https://openalex.org/W2080592089","https://openalex.org/W2081373884","https://openalex.org/W2097561580","https://openalex.org/W2106625514","https://openalex.org/W2118532220","https://openalex.org/W2120585153","https://openalex.org/W2132587889","https://openalex.org/W2140311411","https://openalex.org/W2144481293","https://openalex.org/W2152496451","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2158069650","https://openalex.org/W2169150396","https://openalex.org/W2169875292","https://openalex.org/W2169880332","https://openalex.org/W2208481289","https://openalex.org/W2398736067","https://openalex.org/W2534060050","https://openalex.org/W2535359146","https://openalex.org/W4250814284","https://openalex.org/W6635987275","https://openalex.org/W6662613461"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Due":[0],"to":[1,27,102],"their":[2],"massive":[3],"computational":[4,73],"power,":[5],"graphics":[6],"processing":[7],"units":[8],"(GPUs)":[9],"have":[10],"become":[11],"a":[12,65],"popular":[13],"platform":[14],"for":[15,93],"executing":[16,33],"general":[17],"purpose":[18],"parallel":[19],"applications.":[20],"GPU":[21,67,76],"programming":[22],"models":[23],"allow":[24],"the":[25,34,72],"programmer":[26],"create":[28],"thousands":[29],"of":[30,86],"threads,":[31],"each":[32],"same":[35],"computing":[36],"kernel.":[37],"GPUs":[38],"exploit":[39],"this":[40,94],"parallelism":[41],"in":[42,82],"two":[43],"ways.":[44],"First,":[45],"threads":[46],"are":[47,61,78,95],"grouped":[48],"into":[49],"fixed-size":[50],"SIMD":[51],"batches":[52],"known":[53],"as":[54],"warps,":[55],"and":[56,99],"second,":[57],"many":[58],"such":[59],"warps":[60],"concurrently":[62],"executed":[63],"on":[64,75],"single":[66],"core.":[68],"Despite":[69],"these":[70],"techniques,":[71],"resources":[74],"cores":[77],"still":[79],"underutilized,":[80],"resulting":[81],"performance":[83],"far":[84],"short":[85],"what":[87],"could":[88],"be":[89],"delivered.":[90],"Two":[91],"reasons":[92],"conditional":[96],"branch":[97],"instructions":[98],"stalls":[100],"due":[101],"long":[103],"latency":[104],"operations.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":40},{"year":2017,"cited_by_count":51},{"year":2016,"cited_by_count":56},{"year":2015,"cited_by_count":63},{"year":2014,"cited_by_count":43},{"year":2013,"cited_by_count":39},{"year":2012,"cited_by_count":19}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
